© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108297
    Prev
    Next
    INDEX
    Explanations

    licenses, code, and configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çijĽ
    -0.28
    ç»Ļå®Ŀå®Ŀ
    -0.24
     tying
    -0.24
    å±ħ室
    -0.24
    azar
    -0.24
    åĴ»
    -0.24
    媵
    -0.23
    ç¿¥
    -0.23
    俨
    -0.23
    agic
    -0.23
    POSITIVE LOGITS
    imas
    0.28
    éģĵ
    0.28
    æĸ°å±ĢéĿ¢
    0.28
    éra
    0.26
    æľ¬ç½ijç«Ļ
    0.26
    èĤ¥
    0.25
    мÑĭ
    0.25
    ima
    0.25
    AnimationFrame
    0.24
    群ä¼Ĺ
    0.24
    Activations Density 0.007%

    No Known Activations